Contextualized and Personalized Math Word Problem Generation Using GPT and Authentic Contextual Recognition

This paper introduced an interactive system for generating contextualized and personalized mathematic word problems (MWP) from authentic contexts using the Generative Pre-trained Transformers (GPT). Our proposed Automatic Question Generation (AQG) system comprises (1) the authentic contextual information acquisition through image recognition by TensorFlow and augmented reality (AR) measurement through AR Core, (2) a personalized mechanism based on instructional prompts to generate three difficulty levels for learner's different needs, and (3) MWP generation through GPT with authentic contextual information and personalized needs. A quasi-experiment was conducted by recruiting 51 fifth-grade students to evaluate the effectiveness of the proposed AQG on their geometry learning performance. The results revealed that students who learned with the proposed AQG outperformed students who learned with a decontextualized way on geometry learning performances. Therefore, our proposed AQG is useful for promoting mathematic problem-solving activity in an authentic context.